Digital Mapping of Root-Zone Soil Moisture Using UAV-Based Multispectral Data in a Kiwifruit Orchard of Northwest China

Abstract

Accurate estimation of root-zone soil moisture (SM) is of great significance for accurate irrigation management. This study was purposed to identify planted-by-planted mapping of root-zone SM on three critical fruit growth periods based on UAV multispectral images using three machine learning (ML) algorithms in a kiwifruit orchard in Shaanxi, China. Several spectral variables were selected based on variable importance (VIP) rankings, including reflectance Ri at wavelengths 560, 668, 740, and 842 nm. Results indicated that the VIP method effectively reduced 42 vegetation indexes (VIs) to less than 7 with an evaluation accuracy of root-zone SM models. Compared with deep root-zone SM models (SM40 and SM60), shallow root-zone SM models (SM10, SM20, and SM30) have better performance (R2 from 0.65 to 0.82, RRMSE from 0.02 to 0.03, MAE from 0.20 to 0.54) in the three fruit growth stages. Among three ML algorithms, random forest models were recommended for simulating kiwi root-zone SM during the critical fruit growth period. Overall, the proposed planted-by-planted root-zone SM estimation approach can be considered a great tool to upgrade the toolbox of the growers in site-specific field management for the high spatiotemporal resolution of SM maps.

Evaluation of Precipitation Forecast by the Operational China Meteorological Administration Mesoscale Model During the 2020 Meiyu Period

“…The WRF model is employed as the forecast system, and the data assimilation of the inner domain employs the three‐dimensional variation assimilation and cloud analysis of the Advanced Regional Prediction System. The observation data assimilated by PWAFS includes the surface stations, upper air soundings, the cross‐track infrared sounder, the advanced Himawari imager radiance, radar reflectivity and radial wind data (Zhu et al., 2023). The physical parameterization schemes used by the outer domain of PWAFS include the Thompson microphysics scheme (Thompson et al., 2008), RRTM longwave (Mlawer et al., 1997) and Goddard shortwave radiation transfer schemes (Chou, 1994), YSU boundary layer scheme (Hong et al., 2006), Noah land surface model (Chen & Dudhia, 2001), and Kain–Fritsch (KF) cumulus convection scheme (Kain & Fritsch, 1993).…”

“…The intensity of precipitation predicted by the CPR model was closer to the observations, while the global forecasts with coarser resolution often underestimated the proportion of heavy rainfall. In the current study, in addition to the CMA‐MESO and global forecasts, a local numerical model forecasting system operated by the Jiangsu Meteorological Bureau, that is, the Precise Weather Analysis and Prediction System (PWAFS) (Zhu et al., 2023) that uses the WRF model as the core forecasting model, was also selected for comparison purposes. The advantages and disadvantages of each model regarding prediction of the distribution and intensity of Meiyu precipitation were investigated.…”

Improving Subseasonal‐To‐Seasonal Prediction of Summer Extreme Precipitation Over Southern China Based on a Deep Learning Method

“…Meanwhile, considering the dynamic backgrounds of precipitation, the inclusion of additional forecast variables into the postprocessing framework may also provide additional opportunities for improving S2S precipitation forecasts (Feng et al., 2022; L. Zhang et al., 2023). These statistical postprocessing approaches could improve forecast skills to a certain extent, while limitations still exist due to their focusing on linear characteristics of the elements and taking little consideration on the spatial features of biases (Lyu et al., 2021; S. Zhu et al., 2023b).…”

An Improved UAV-Based ATI Method Incorporating Solar Radiation for Farm-Scale Bare Soil Moisture Measurement

“…Soil moisture is critical for agriculture and crop management [1,2]. In recent decades, the use of UAV-based remote sensing for soil moisture monitoring has developed rapidly due to its inherent advantages of having high spatial resolution, flexible work arrangement, and ease of operation [3][4][5][6][7][8]. Remote sensing for soil moisture monitoring mainly uses visible-near-infrared, thermal infrared, and microwave-based imaging technologies [9][10][11][12][13][14][15].…”